Multispectral image panchromatic sharpening method and system based on spatial-spectral fusion network
A multi-spectral image, fusion network technology, applied in image enhancement, image analysis, graphic image conversion and other directions, can solve problems such as distortion and hyperspectral, and achieve the effect of improving utilization, stable fusion results, and improving information utilization.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] Such as figure 1 As shown, in order to solve the problems of spatial information ambiguity and spectral distortion in the prior art to improve the spatial resolution. This embodiment provides a multi-spectral image panchromatic sharpening method based on a spatial-spectral fusion network. This embodiment uses this method as an example to illustrate a server. It can be understood that this method can also be applied to a terminal, or The application includes terminals, servers and systems, and is realized through the interaction between terminals and servers. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or it can provide cloud services, cloud database, cloud computing, cloud function, cloud storage, network server, cloud communication, intermediate Cloud servers for basic cloud computing services such as software services, domain name services, security service CDN, and big data and ar...
Embodiment approach
[0049] As one or more implementations, before step (2), it includes: performing a quadruple upsampling operation on the low spatial resolution multispectral image to obtain a low spatial resolution image with the same size as the high spatial resolution panchromatic image P The initial multispectral image LM.
[0050] As one or more implementations, such as figure 2 As shown, step (4) includes:
[0051] Step (4-1): Input the multispectral image with low spatial resolution and the panchromatic image with high spatial resolution into the stacking module of the fusion network to obtain the first fusion feature map f 1 ;
[0052] Step (4-2): The first multispectral image feature map ms extracted by the first-level spectral information extraction network 1 , the first panchromatic image feature map pan extracted by the first-level spatial information extraction network 1 Input the first fusion block of the fusion network to calculate the first multispectral image feature map m...
Embodiment 2
[0096] This embodiment provides a multi-spectral image panchromatic sharpening system based on a spatial-spectral fusion network.
[0097] A multi-spectral image panchromatic sharpening system based on spatial-spectral fusion network, including:
[0098] An acquisition module configured to: acquire a low spatial resolution multispectral image and a high spatial resolution panchromatic image;
[0099] The spectral information extraction network module is configured to: perform information extraction step by step through the spectral information extraction network for multispectral images with low spatial resolution;
[0100] The spatial information extraction network module is configured to: extract the panchromatic image with high spatial resolution through the spatial information extraction network for step-by-step information extraction;
[0101] The fusion network module is configured to: average the multispectral image feature map extracted by each level of spectral infor...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More